activity
20222024
most citedDFormer: Diffusion-guided Transformer for Universal Image Segmentation

7 citations · 14 across the 9 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV20242 cited

Raformer: Redundancy-Aware Transformer for Video Wire Inpainting

Zhong Ji, Yimu Su, Yan Zhang +3

Video Wire Inpainting (VWI) is a prominent application in video inpainting, aimed at flawlessly removing wires in films or TV series, offering significant time and labor savings co…

cs.CV2024

Joint Attention-Guided Feature Fusion Network for Saliency Detection of Surface Defects

Xiaoheng Jiang, Feng Yan, Yang Lu +6

Surface defect inspection plays an important role in the process of industrial manufacture and production. Though Convolutional Neural Network (CNN) based defect inspection methods…

cs.CV20237 cited

DFormer: Diffusion-guided Transformer for Universal Image Segmentation

Hefeng Wang, Jiale Cao, Rao Muhammad Anwer +3

This paper introduces an approach, named DFormer, for universal image segmentation. The proposed DFormer views universal image segmentation task as a denoising process using a diff…

cs.CV20231 cited

LEAPS: End-to-End One-Step Person Search With Learnable Proposals

Zhiqiang Dong, Jiale Cao, Rao Muhammad Anwer +3

We propose an end-to-end one-step person search approach with learnable proposals, named LEAPS. Given a set of sparse and learnable proposals, LEAPS employs a dynamic person search…

cs.CV20231 cited

USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval

Yan Zhang, Zhong Ji, Di Wang +2

As a fundamental and challenging task in bridging language and vision domains, Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant…

cs.CV20221 cited

Multi-scale Feature Aggregation for Crowd Counting

Xiaoheng Jiang, Xinyi Wu, Hisham Cholakkal +5

Convolutional Neural Network (CNN) based crowd counting methods have achieved promising results in the past few years. However, the scale variation problem is still a huge challeng…